© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 14873
    Prev
    Next
    INDEX
    Explanations

    concepts related to collective impact and social justice issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \{\\
    -0.75
    WithIOException
    -0.62
    httphttps
    -0.59
     beats
    -0.57
    (!__
    -0.56
    IsMutable
    -0.56
     bain
    -0.54
    <_>
    -0.53
     beat
    -0.53
    oriam
    -0.52
    POSITIVE LOGITS
     concernés
    0.55
     downstream
    0.55
    AutoScaleMode
    0.54
    InsertCommand
    0.54
    tonsoft
    0.54
    ValueStyle
    0.50
    tadır
    0.50
    AndroidJUnit
    0.50
     sociais
    0.48
    发表于
    0.48
    Activations Density 0.083%

    No Known Activations